MT-Mol: Multi Agent System with Tool-based Reasoning for Molecular Optimization

Hyomin Kim, Yunhui Jang, Sungsoo Ahn


Abstract
Large language models (LLMs) have large potential for molecular optimization, as they can gather external chemistry tools and enable collaborative interactions to iteratively refine molecular candidates. However, this potential remains underexplored, particularly in the context of structured reasoning, interpretability, and comprehensive tool-grounded molecular optimization. To address this gap, we introduce MT-Mol, a multi-agent framework for molecular optimization that leverages tool-guided reasoning and role-specialized LLM agents. Our system incorporates comprehensive RDKit tools, categorized into five distinct domains: structural descriptors, electronic and topological features, fragment-based functional groups, molecular representations, and miscellaneous chemical properties. Each category is managed by an expert analyst agent, responsible for extracting task-relevant tools and enabling interpretable, chemically grounded feedback. MT-Mol produces molecules with tool-aligned and stepwise reasoning through the interaction between the analyst agents, a molecule-generating scientist, a reasoning-output verifier, and a reviewer agent. As a result, we show that our framework shows the state-of-the-art performance of the PMO-1K benchmark on 15 out of 23 tasks and outperforms LLM baselines on ChemCoTBench benchmark.
Anthology ID:
2025.findings-emnlp.619
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11544–11573
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.619/
DOI:
Bibkey:
Cite (ACL):
Hyomin Kim, Yunhui Jang, and Sungsoo Ahn. 2025. MT-Mol: Multi Agent System with Tool-based Reasoning for Molecular Optimization. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 11544–11573, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
MT-Mol: Multi Agent System with Tool-based Reasoning for Molecular Optimization (Kim et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.619.pdf
Checklist:
 2025.findings-emnlp.619.checklist.pdf